He stared at the official-looking document. It lay on the worn coffee table, surrounded by the remnants of his takeout dinner. Michael felt a peculiar weight in his chest, a pressure that made it difficult to breathe. The apartment, usually a haven, suddenly felt constricting, the walls closing in.

He rose abruptly and began to pace. Each footstep on the creaky floorboards seemed to amplify the silence. He ran a hand through his already disheveled hair, leaving it standing on end. He needed a drink, a very strong drink.

His eyes darted around the room, taking in every detail: the overflowing ashtray, the stack of unpaid bills, the empty pizza box. The evidence of his life felt both meaningless and impossibly heavy.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

This story is one of 1,000 stories generated for the emotion tense. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 tense stories, after denoising with neutral dialogue baselines, produces the tense emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tense vector is projected through the unembedding matrix.

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198